What We’re Looking For

We’re opening an office in London, UK and looking for AI Engineers to design and deploy production-grade AI systems powered by LLMs.

At Distyl, AI Engineers work directly with Fortune 500 companies to transform complex workflows using cutting-edge AI. You’ll build and ship real-world AI applications — from intelligent agents to full-stack AI products — and see them operate at scale in mission-critical environments.

This role is highly hands-on. You’ll collaborate closely with customers, define system architectures, and build reliable, high-impact AI systems from prototype to production. Engineers at Distyl also help shape technical direction across major customer engagements, guiding enterprise teams through AI adoption and deployment.

Key Responsibilities

• Build Production AI Systems: Design, develop, and deploy robust AI applications using LLMs, including prompt engineering, agent workflows, tool use, and full-stack AI products

• Work Directly with Customers: Partner closely with enterprise stakeholders to understand complex problems and translate them into impactful AI solutions

• Lead System Architecture: Design scalable architectures for production AI systems, balancing performance, reliability, cost, and maintainability

• Develop Our Internal Platform: Contribute to Distillery, our internal LLM application platform, by building reusable infrastructure, tools, and workflows used across customer deployments

• Evaluate AI Systems Rigorously: Develop evaluation frameworks that measure model performance across accuracy, latency, cost, reliability, and safety

• Ship Production-Grade Systems: Ensure systems meet high standards for observability, reliability, security, and maintainability

• Raise the Engineering Bar: Improve development workflows, evaluation practices, and deployment strategies as our AI platform continues to evolve

Who You Are

• 3+ years of professional software engineering experience

• Strong proficiency in Python or TypeScript

• Experience building and deploying LLM-powered applications or AI agents in production

• Experience with modern LLM tooling such as LangChain, LlamaIndex, Guardrails, MCP, or agent frameworks

• Experience implementing RAG pipelines, tool use, or multi-step AI workflows

• Strong understanding of AI system evaluation, debugging, and observability

• Experience building reliable production systems with modern DevOps practices

• Experience deploying AI systems in enterprise environments is a plus

• Experience working across cloud platforms (AWS, GCP, or Azure) is a plus

• Experience with agent architectures and long-horizon task execution is a plus

• Familiarity with responsible AI practices, including auditability and governance is a plus

What We Offer

• Competitive salary, meaningful equity, and a comprehensive benefits package

• Workplace Pension Scheme with employer contributions

• Private Medical Insurance (PMI) offered

• Flexible Time Off + Holidays

• Lunch provided on office days

• Access to state-of-the-art models, generous usage of modern AI tools, and real-world business problems

• Ownership of high-impact projects across top enterprises

• A mission-driven, fast-moving culture that prizes curiosity, pragmatism, and excellence

#LI-Hybrid